Examples of AlphabetFactory

Examples of org.fnlp.ml.types.alphabet.AlphabetFactory

48
49
50
51
52
53
54
55
56
57
58
59
60
    BufferedReader rd = new BufferedReader(
          new InputStreamReader(new FileInputStream(from), "gbk"));
   
    ObjectOutputStream out = new ObjectOutputStream(new BufferedOutputStream (
        new GZIPOutputStream (new FileOutputStream(to))));
    AlphabetFactory factory = AlphabetFactory.buildFactory();
    LabelAlphabet labels = factory.DefaultLabelAlphabet();
    IFeatureAlphabet features = factory.DefaultFeatureAlphabet();;
    String s;
    rd.readLine();  //version
    List lst = new ArrayList();      //template
    while(true) {
      s = rd.readLine();
View Full Code Here

Examples of org.fnlp.ml.types.alphabet.AlphabetFactory

62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
  public void train(Reader reader, String modelFile) throws Exception {
    /**
     * 分类模型
     */
    //建立字典管理器
    AlphabetFactory af = AlphabetFactory.buildFactory();

    //使用n元特征
    Pipe ngrampp = new NGram(new int[] {1,2});
    //将字符特征转换成字典索引
    Pipe indexpp = new StringArray2IndexArray(af);
    //将目标值对应的索引号作为类别
    Pipe targetpp = new Target2Label(af.DefaultLabelAlphabet());   

    //建立pipe组合
    SeriesPipes pp = new SeriesPipes(new Pipe[]{ngrampp,targetpp,indexpp});
   
    SeriesPipes  pp2 = new SeriesPipes(new Pipe[]{prePipe, ngrampp,targetpp,indexpp});
   
    InstanceSet instset = new InstanceSet(pp2,af);



    //读入数据，并进行数据处理
    instset.loadThruStagePipes(reader);

    /**
     * 建立分类器
     */   
    OnlineTrainer trainer = new OnlineTrainer(af,100);
    trainer.c = 0.01f;
    pclassifier = trainer.train(instset);
    pp.removeTargetPipe();
    pclassifier.setPipe(pp);
    af.setStopIncrement(true);

    //将分类器保存到模型文件
    pclassifier.saveTo(modelFile); 
  }
View Full Code Here

Examples of org.fnlp.ml.types.alphabet.AlphabetFactory

55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
    Pipe s2spp=new Strings2StringArray();
    /**
     * Bayes
     */
    //建立字典管理器
    AlphabetFactory af = AlphabetFactory.buildFactory();
    //使用n元特征
    Pipe ngrampp = new NGram(new int[] {2,3});
    //将字符特征转换成字典索引; 
    Pipe sparsepp=new StringArray2SV(af);
    //将目标值对应的索引号作为类别
    Pipe targetpp = new Target2Label(af.DefaultLabelAlphabet()); 
    //建立pipe组合
    SeriesPipes pp = new SeriesPipes(new Pipe[]{removepp,segpp,s2spp,targetpp,sparsepp});

    System.out.print("\nReading data......\n");
    InstanceSet instset = new InstanceSet(pp,af); 
    Reader reader = new MyDocumentReader(trainDataPath,"gbk");
    instset.loadThruStagePipes(reader);
    System.out.print("..Reading data complete\n");
   
    //将数据集分为训练是和测试集
    System.out.print("Sspliting....");
    float percent = 0.8f;
    InstanceSet[] splitsets = instset.split(percent);
   
    InstanceSet trainset = splitsets[0];
    InstanceSet testset = splitsets[1]; 
    System.out.print("..Spliting complete!\n");

    System.out.print("Training...\n");
    af.setStopIncrement(true);
    BayesTrainer trainer=new BayesTrainer();
    BayesClassifier classifier= (BayesClassifier) trainer.train(trainset);
    System.out.print("..Training complete!\n");
    System.out.print("Saving model...\n");
    classifier.saveTo(bayesModelFile); 
View Full Code Here

Examples of org.fnlp.ml.types.alphabet.AlphabetFactory

19
20
21
22
23
24
25
26
27
28
*
*/
public class BayesTrainer{

  public AbstractClassifier train(InstanceSet trainset) {
    AlphabetFactory af=trainset.getAlphabetFactory();
    SeriesPipes pp=(SeriesPipes) trainset.getPipes();
    pp.removeTargetPipe();
    return train(trainset,af,pp);
  }
View Full Code Here

Examples of org.fnlp.ml.types.alphabet.AlphabetFactory

58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
   
    String train = "./example-data/sequence/train.txt";
    String testfile = "./example-data/sequence/test.txt";
    String templateFile="./example-data/sequence/template";
    AlphabetFactory factory;
    Pipe featurePipe;
    TempletGroup templets;

    templets = new TempletGroup();
    templets.load(templateFile);
    factory = AlphabetFactory.buildFactory();

    /**
     * 标签字典。转为0、1、2、...
     */
    LabelAlphabet labels = factory.DefaultLabelAlphabet();
    /**
     * 特征字典
     */
    IFeatureAlphabet features = factory.DefaultFeatureAlphabet();
    // 将样本通过Pipe抽取特征
   
    featurePipe = new Sequence2FeatureSequence(templets, features, labels);

    Pipe pipe = new SeriesPipes(new Pipe[] { new Target2Label(labels), featurePipe });
View Full Code Here

Examples of org.fnlp.ml.types.alphabet.AlphabetFactory

57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
    CWSTagger tag = new CWSTagger("../models/seg.m");
    Pipe segpp=new CNPipe(tag);
    Pipe s2spp=new Strings2StringArray();
   
    //建立字典管理器
    AlphabetFactory af = AlphabetFactory.buildFactory();
    //使用n元特征
    Pipe ngrampp = new NGram(new int[] {2,3});
    //将字符特征转换成字典索引; 
    Pipe sparsepp=new StringArray2SV(af);
    //将目标值对应的索引号作为类别
    Pipe targetpp = new Target2Label(af.DefaultLabelAlphabet()); 
    //建立pipe组合
    SeriesPipes pp = new SeriesPipes(new Pipe[]{removepp,segpp,s2spp,targetpp,sparsepp});

    /**
     * Knn
     */
    System.out.print("\nKnn\n");
    System.out.print("\nReading data......\n");
    long time_mark=System.currentTimeMillis();
    InstanceSet instset = new InstanceSet(pp,af); 
    Reader reader = new MyDocumentReader(trainDataPath,"gbk");
    instset.loadThruStagePipes(reader);
    System.out.print("..Reading data complete "+(System.currentTimeMillis()-time_mark)+"(ms)\n");
   
    //将数据集分为训练是和测试集
    System.out.print("Sspliting....");
    float percent = 0.9f;
    InstanceSet[] splitsets = instset.split(percent);
   
    InstanceSet trainset = splitsets[0];
    InstanceSet testset = splitsets[1]; 
    System.out.print("..Spliting complete!\n");
   
    System.out.print("Training Knn...\n");
    time_mark=System.currentTimeMillis();
    SparseVectorSimilarity sim=new SparseVectorSimilarity();
    pp.removeTargetPipe();
    KNNClassifier knn=new KNNClassifier(trainset, pp, sim, af, 9); 
    af.setStopIncrement(true); 
   
    ItemFrequency tf=new ItemFrequency(trainset);
    FeatureSelect fs=new FeatureSelect(tf.getFeatureSize());
    long time_train=System.currentTimeMillis()-time_mark;
   
View Full Code Here

Examples of org.fnlp.ml.types.alphabet.AlphabetFactory

56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
  public static void main(String[] args) throws Exception {

   
    //建立字典管理器
    AlphabetFactory af = AlphabetFactory.buildFactory();
   
    //使用n元特征
    Pipe ngrampp = new NGram(new int[] {2,3 });
    //将字符特征转换成字典索引
    Pipe indexpp = new StringArray2IndexArray(af);
    //将目标值对应的索引号作为类别
    Pipe targetpp = new Target2Label(af.DefaultLabelAlphabet());   
   
    //建立pipe组合
    SeriesPipes pp = new SeriesPipes(new Pipe[]{ngrampp,targetpp,indexpp});
   
    InstanceSet instset = new InstanceSet(pp,af);
   
    //用不同的Reader读取相应格式的文件
    Reader reader = new FileReader(trainDataPath,"UTF-8",".data");
   
    //读入数据，并进行数据处理
    instset.loadThruStagePipes(reader);
       
    float percent = 0.8f;
   
    //将数据集分为训练是和测试集
    InstanceSet[] splitsets = instset.split(percent);
   
    InstanceSet trainset = splitsets[0];
    InstanceSet testset = splitsets[1]; 
   
    /**
     * 建立分类器
     */   
    OnlineTrainer trainer = new OnlineTrainer(af);
    Linear pclassifier = trainer.train(trainset);
    pp.removeTargetPipe();
    pclassifier.setPipe(pp);
    af.setStopIncrement(true);
   
    //将分类器保存到模型文件
    pclassifier.saveTo(modelFile); 
    pclassifier = null;
   
View Full Code Here

Examples of org.fnlp.ml.types.alphabet.AlphabetFactory

43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
  public static void main(String[] args) throws Exception {
    /**
     * Bayes
     */
    //建立字典管理器
    AlphabetFactory af = AlphabetFactory.buildFactory();
    //使用n元特征
    Pipe ngrampp = new NGram(new int[] {2,3});
    //将字符特征转换成字典索引; 
    Pipe sparsepp=new StringArray2SV(af);
    //将目标值对应的索引号作为类别
    Pipe targetpp = new Target2Label(af.DefaultLabelAlphabet()); 
    //建立pipe组合
    SeriesPipes pp = new SeriesPipes(new Pipe[]{ngrampp,targetpp,sparsepp});

    System.out.print("\nReading data......\n");
    InstanceSet instset = new InstanceSet(pp,af); 
    Reader reader = new MyDocumentReader(trainDataPath,"gbk");
    instset.loadThruStagePipes(reader);
    System.out.print("..Reading data complete\n");
   
    //将数据集分为训练是和测试集
    System.out.print("Sspliting....");
    float percent = 0.9f;
    InstanceSet[] splitsets = instset.split(percent);
   
    InstanceSet trainset = splitsets[0];
    InstanceSet testset = splitsets[1]; 
    System.out.print("..Spliting complete!\n");

    System.out.print("Training...\n");
    BayesTrainer trainer=new BayesTrainer();
    BayesClassifier classifier= (BayesClassifier) trainer.train(trainset);
    pp.removeTargetPipe();
    classifier.setPipe(pp);
    af.setStopIncrement(true);
    System.out.print("..Training complete!\n");
    System.out.print("Saving model...\n");
    classifier.saveTo(bayesModelFile); 
    classifier = null;
    System.out.print("..Saving model complete!\n");
    /**
     * 测试
     */
    System.out.print("Loading model...\n");
    BayesClassifier bayes;
    bayes =BayesClassifier.loadFrom(bayesModelFile);
//    bayes =classifier;
    System.out.print("..Loading model complete!\n");
   
    System.out.println("Testing Bayes...");
    int count=0;
    for(int i=0;i<testset.size();i++){
      Instance data = testset.getInstance(i);
      Integer gold = (Integer) data.getTarget();
      Predict<String> pres=bayes.classify(data, Type.STRING, 3);
      String pred_label=pres.getLabel();
//      String pred_label = bayes.getStringLabel(data);
      String gold_label = bayes.getLabel(gold);
     
      if(pred_label.equals(gold_label)){
        //System.out.println(pred_label+" : "+testsetbayes.getInstance(i).getTempData());
        count++;
      }
      else{
//        System.err.println(gold_label+"->"+pred_label+" : "+testset.getInstance(i).getTempData());
//        for(int j=0;j<3;j++)
//          System.out.println(pres.getLabel(j)+":"+pres.getScore(j));
      }
    }
    int bayesCount=count;
    System.out.println("..Testing Bayes complete!");
    System.out.println("Bayes Precision:"+((float)bayesCount/testset.size())+"("+bayesCount+"/"+testset.size()+")");


    /**
     * Knn
     */
    System.out.print("\nKnn\n");
    //建立字典管理器
    AlphabetFactory af2 = AlphabetFactory.buildFactory();
    //使用n元特征
    ngrampp = new NGram(new int[] {2,3});
    //将字符特征转换成字典索引; 
    sparsepp=new StringArray2SV(af2);
    //将目标值对应的索引号作为类别
    targetpp = new Target2Label(af2.DefaultLabelAlphabet()); 
    //建立pipe组合
    pp = new SeriesPipes(new Pipe[]{ngrampp,targetpp,sparsepp});

    System.out.print("Init dataset...");
    trainset.setAlphabetFactory(af2); 
    trainset.setPipes(pp); 
    testset.setAlphabetFactory(af2); 
    testset.setPipes(pp);     
    for(int i=0;i<trainset.size();i++){
      Instance inst=trainset.get(i);
      inst.setData(inst.getSource());
      int target_id=Integer.parseInt(inst.getTarget().toString());
      inst.setTarget(af.DefaultLabelAlphabet().lookupString(target_id));
      pp.addThruPipe(inst);
    }   
    for(int i=0;i<testset.size();i++){
      Instance inst=testset.get(i);
      inst.setData(inst.getSource());
      int target_id=Integer.parseInt(inst.getTarget().toString());
      inst.setTarget(af.DefaultLabelAlphabet().lookupString(target_id));
      pp.addThruPipe(inst);
    }

    System.out.print("complete!\n");
    System.out.print("Training Knn...\n");
    SparseVectorSimilarity sim=new SparseVectorSimilarity();
    pp.removeTargetPipe();
    KNNClassifier knn=new KNNClassifier(trainset, pp, sim, af2, 7); 
    af2.setStopIncrement(true); 
    System.out.print("..Training compelte!\n");
    System.out.print("Saving model...\n");
    knn.saveTo(knnModelFile); 
    knn = null;
    System.out.print("..Saving model compelte!\n");

   
    System.out.print("Loading model...\n");
    knn =KNNClassifier.loadFrom(knnModelFile);
    System.out.print("..Loading model compelte!\n");
    System.out.println("Testing Knn...\n");
    count=0;
    for(int i=0;i<testset.size();i++){
      Instance data = testset.getInstance(i);
      Integer gold = (Integer) data.getTarget();
      Predict<String> pres=(Predict<String>) knn.classify(data, Type.STRING, 3);
      String pred_label=pres.getLabel();
      String gold_label = knn.getLabel(gold);
     
      if(pred_label.equals(gold_label)){
        //System.out.println(pred_label+" : "+testsetknn.getInstance(i).getTempData());
        count++;
      }
      else{
//        System.err.println(gold_label+"->"+pred_label+" : "+testset.getInstance(i).getTempData());
//        for(int j=0;j<3;j++)
//          System.out.println(pres.getLabel(j)+":"+pres.getScore(j));
      }
    }
    int knnCount=count;
    System.out.println("..Testing Knn Complete");
    System.out.println("Bayes Precision:"+((float)bayesCount/testset.size())+"("+bayesCount+"/"+testset.size()+")");
    System.out.println("Knn Precision:"+((float)knnCount/testset.size())+"("+knnCount+"/"+testset.size()+")");
   
    //建立字典管理器
    AlphabetFactory af3 = AlphabetFactory.buildFactory();
    //使用n元特征
    ngrampp = new NGram(new int[] {2,3 });
    //将字符特征转换成字典索引
    Pipe indexpp = new StringArray2IndexArray(af3);
    //将目标值对应的索引号作为类别
    targetpp = new Target2Label(af3.DefaultLabelAlphabet());   
   
    //建立pipe组合
    pp = new SeriesPipes(new Pipe[]{ngrampp,targetpp,indexpp});
   
    trainset.setAlphabetFactory(af3); 
View Full Code Here

Examples of org.fnlp.ml.types.alphabet.AlphabetFactory

54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
  public static void main(String[] args) throws Exception {

   
    //建立字典管理器
    AlphabetFactory af = AlphabetFactory.buildFactory();
   
    //使用n元特征
    Pipe ngrampp = new NGram(new int[] {2,3 });
    //将字符特征转换成字典索引
    Pipe indexpp = new StringArray2IndexArray(af);
    //将目标值对应的索引号作为类别
    Pipe targetpp = new Target2Label(af.DefaultLabelAlphabet());   
   
    //建立pipe组合
    SeriesPipes pp = new SeriesPipes(new Pipe[]{ngrampp,targetpp,indexpp});
   
    InstanceSet trainset = new InstanceSet(pp,af);
    InstanceSet testset = new InstanceSet(pp,af);
   
    //用不同的Reader读取相应格式的文件
    Reader reader = new DocumentReader(trainDataPath);
   
    //读入数据，并进行数据处理
    trainset.loadThruStagePipes(reader);
   
    reader = new DocumentReader(testDataPath);
     
    testset.loadThruStagePipes(reader);
   
   
    /**
     * 建立分类器
     */   
    OnlineTrainer trainer = new OnlineTrainer(af);
    Linear pclassifier = trainer.train(trainset);
    pp.removeTargetPipe();
    pclassifier.setPipe(pp);
    af.setStopIncrement(true);
   
    //将分类器保存到模型文件
    pclassifier.saveTo(modelFile); 
    pclassifier = null;
   
View Full Code Here

Examples of org.fnlp.ml.types.alphabet.AlphabetFactory

60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
    }
    String res = bayes.getStringLabel(inst);
    System.out.println("xxx"); 
    System.out.println("类别："+ res); 
    //建立字典管理器
    AlphabetFactory af = AlphabetFactory.buildFactory();
   
    //使用n元特征
    Pipe ngrampp = new NGram(new int[] {1,2});
    //分词
//    CWSTagger tag = new CWSTagger("../models/seg.m");
//    Pipe segpp=new CNPipe(tag);
    //将字符特征转换成字典索引
    Pipe indexpp = new StringArray2IndexArray(af); 
    Pipe sparsepp=new StringArray2SV(af);
    //将目标值对应的索引号作为类别
    Pipe targetpp = new Target2Label(af.DefaultLabelAlphabet()); 
    //建立pipe组合
    SeriesPipes pp = new SeriesPipes(new Pipe[]{ngrampp,targetpp,sparsepp});
   
    InstanceSet instset = new InstanceSet(pp,af);
   
View Full Code Here
TOP
Copyright © 2018 www.massapi.com. All rights reserved.
All source code are property of their respective owners. Java is a trademark of Sun Microsystems, Inc and owned by ORACLE Inc. Contact coftware#gmail.com.